Violence-MFAS: Audio-Visual Violence Detection Using Multimodal Fusion Architecture Search.

Dan Si Qing Ye Jindi Lv Yuhao Zhou Jiancheng Lv

Published in: ICONIP (14) (2023)

Keyphrases

audio visual
multimodal fusion
multi modal
relevance feedback
visual information
multimedia
high robustness
visual data
multi stream
object detection
data points
multimodal interfaces